Jasmin Hundal MD, Benson A Babu MD, MBA

Introduction
Gait analysis provide useful information of the patient’s underlying medical condition.
Artificial Intelligence is a rapid emerging medical decision making support and predictive analytic tool. We compare different deep learning and classic learning methods in geriatric patient gait assessment classification the accuracy, sensitivity, and specificity.

Study Design Systematic Review
Cross-sectional studies extracted with standard search strategies
Search Engines:
PubMed/MEDLINE • EMBASE (or Scopus) • Cochrane Library • Google Scholar • Web of Science • IEEEXplore • DBLP

Primary analysis
Deep learning methods vs. Classical machine learning methods for peri-operative care
Deep learning methods and peri-operative predictive analytics

Subgroup Analysis
Comparing specific types of Deep learning classifiers (e.g., CNN, DBN, auto-encoders, etc.) and/or specific types of Classical machine learning methods (e.g., SVM, LDA, etc.)
Outcomes Sensitivity: how well the algorithm recognizes the type of nodule correctly
Specificity: measures the ability of the algorithm to remove the false positives, and a high specificity value means a low rate of misdiagnosis
Accuracy: measures the proportion of data that correctly classified.
Sensitivity-specificity ROC curve and Area under the curve (AUC): other indicators used to evaluate the performance of a classifier.

Conclusion
Deep learning methods are just as accurate, or more than compared to classic machine leaning methods. Subgroup analysis comparing specific classic machine and deep learning methods. Deep learning models are accurate and provide clinical support tool for physicians and insight into assessing patient’s gait, thus underlying medical conditions.